A reference platform with components for collecting data, training, evaluating, and deploying embodied AI systems on AWS.
- [October 2025] We added the first component that demonstrates the fine-tuning pipeline for NVIDIA Isaac GR00T vision-language-action (VLA) model via teleoperation and imitation learning, then deploying for inference on cost-effective SO-ARM100/101.
- Accelerate adoption: End-to-end reference architecture combining AWS managed services with open source, purpose-built for physical/embodied AI.
- Lower the barrier: Train and test in the cloud, then deploy to real robots, cost-effectively and reproducibly.
- Move fast: Re-train overnight in AWS as tasks and environments change.
- Ecosystem enablement: A practical baseline for startups and enterprises to build scalable physical AI pipelines on AWS.
- Cloud-to-robot path: Demonstrates integration from simulation and training to on-device inference.
This repository is organized into modular components. Each component has its own documentation with setup, deployment, and usage instructions.
| Component | Path | Purpose | Docs |
|---|---|---|---|
| NVIDIA Isaac GR00T Training | training/gr00t/ |
Fine-tune NVIDIA Isaac GR00T with teleop/sim data; reproducible workflow on AWS Batch; DCV workstation for monitoring/eval | training/gr00t/README.md |
- Additional VLA backbones and training recipes
- Alternative data generation: teleop, scripted, sim-to-real augmentation, synthetic video
- More embodiments (humanoids, robotic arms, etc.)
- Serving patterns (SageMaker, EKS) and agents (Bedrock, OSS)
- Robust IoT/edge deployment (AWS IoT/Greengrass), safety/telemetry best practices
Review and run security scans before production use. See:
- Each component and its own security considerations and best practices.
- CONTRIBUTING
If you notice a defect, feel free to create an Issue.
Contributions are welcome. Please see CONTRIBUTING and CODE_OF_CONDUCT.
This project is licensed under the MIT-0 License. See LICENSE.
- AWS teams and community projects
- NVIDIA Isaac team and open-source contributors